US20200241958A1 - Memory system and operation method thereof - Google Patents
Memory system and operation method thereof Download PDFInfo
- Publication number
- US20200241958A1 US20200241958A1 US16/683,989 US201916683989A US2020241958A1 US 20200241958 A1 US20200241958 A1 US 20200241958A1 US 201916683989 A US201916683989 A US 201916683989A US 2020241958 A1 US2020241958 A1 US 2020241958A1
- Authority
- US
- United States
- Prior art keywords
- error detection
- data
- memory
- detection code
- read
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03M—CODING; DECODING; CODE CONVERSION IN GENERAL
- H03M13/00—Coding, decoding or code conversion, for error detection or error correction; Coding theory basic assumptions; Coding bounds; Error probability evaluation methods; Channel models; Simulation or testing of codes
- H03M13/03—Error detection or forward error correction by redundancy in data representation, i.e. code words containing more digits than the source words
- H03M13/05—Error detection or forward error correction by redundancy in data representation, i.e. code words containing more digits than the source words using block codes, i.e. a predetermined number of check bits joined to a predetermined number of information bits
- H03M13/09—Error detection only, e.g. using cyclic redundancy check [CRC] codes or single parity bit
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/08—Error detection or correction by redundancy in data representation, e.g. by using checking codes
- G06F11/10—Adding special bits or symbols to the coded information, e.g. parity check, casting out 9's or 11's
- G06F11/1008—Adding special bits or symbols to the coded information, e.g. parity check, casting out 9's or 11's in individual solid state devices
- G06F11/1064—Adding special bits or symbols to the coded information, e.g. parity check, casting out 9's or 11's in individual solid state devices in cache or content addressable memories
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/08—Error detection or correction by redundancy in data representation, e.g. by using checking codes
- G06F11/10—Adding special bits or symbols to the coded information, e.g. parity check, casting out 9's or 11's
- G06F11/1008—Adding special bits or symbols to the coded information, e.g. parity check, casting out 9's or 11's in individual solid state devices
- G06F11/1012—Adding special bits or symbols to the coded information, e.g. parity check, casting out 9's or 11's in individual solid state devices using codes or arrangements adapted for a specific type of error
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/08—Error detection or correction by redundancy in data representation, e.g. by using checking codes
- G06F11/10—Adding special bits or symbols to the coded information, e.g. parity check, casting out 9's or 11's
- G06F11/1004—Adding special bits or symbols to the coded information, e.g. parity check, casting out 9's or 11's to protect a block of data words, e.g. CRC or checksum
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/08—Error detection or correction by redundancy in data representation, e.g. by using checking codes
- G06F11/10—Adding special bits or symbols to the coded information, e.g. parity check, casting out 9's or 11's
- G06F11/1008—Adding special bits or symbols to the coded information, e.g. parity check, casting out 9's or 11's in individual solid state devices
- G06F11/1012—Adding special bits or symbols to the coded information, e.g. parity check, casting out 9's or 11's in individual solid state devices using codes or arrangements adapted for a specific type of error
- G06F11/102—Error in check bits
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/08—Error detection or correction by redundancy in data representation, e.g. by using checking codes
- G06F11/10—Adding special bits or symbols to the coded information, e.g. parity check, casting out 9's or 11's
- G06F11/1008—Adding special bits or symbols to the coded information, e.g. parity check, casting out 9's or 11's in individual solid state devices
- G06F11/1048—Adding special bits or symbols to the coded information, e.g. parity check, casting out 9's or 11's in individual solid state devices using arrangements adapted for a specific error detection or correction feature
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/0223—User address space allocation, e.g. contiguous or non contiguous base addressing
- G06F12/023—Free address space management
- G06F12/0238—Memory management in non-volatile memory, e.g. resistive RAM or ferroelectric memory
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/0223—User address space allocation, e.g. contiguous or non contiguous base addressing
- G06F12/023—Free address space management
- G06F12/0238—Memory management in non-volatile memory, e.g. resistive RAM or ferroelectric memory
- G06F12/0246—Memory management in non-volatile memory, e.g. resistive RAM or ferroelectric memory in block erasable memory, e.g. flash memory
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C29/00—Checking stores for correct operation ; Subsequent repair; Testing stores during standby or offline operation
- G11C29/04—Detection or location of defective memory elements, e.g. cell constructio details, timing of test signals
- G11C29/08—Functional testing, e.g. testing during refresh, power-on self testing [POST] or distributed testing
- G11C29/12—Built-in arrangements for testing, e.g. built-in self testing [BIST] or interconnection details
- G11C29/38—Response verification devices
- G11C29/42—Response verification devices using error correcting codes [ECC] or parity check
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03M—CODING; DECODING; CODE CONVERSION IN GENERAL
- H03M13/00—Coding, decoding or code conversion, for error detection or error correction; Coding theory basic assumptions; Coding bounds; Error probability evaluation methods; Channel models; Simulation or testing of codes
- H03M13/29—Coding, decoding or code conversion, for error detection or error correction; Coding theory basic assumptions; Coding bounds; Error probability evaluation methods; Channel models; Simulation or testing of codes combining two or more codes or code structures, e.g. product codes, generalised product codes, concatenated codes, inner and outer codes
- H03M13/2906—Coding, decoding or code conversion, for error detection or error correction; Coding theory basic assumptions; Coding bounds; Error probability evaluation methods; Channel models; Simulation or testing of codes combining two or more codes or code structures, e.g. product codes, generalised product codes, concatenated codes, inner and outer codes using block codes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2212/00—Indexing scheme relating to accessing, addressing or allocation within memory systems or architectures
- G06F2212/10—Providing a specific technical effect
- G06F2212/1016—Performance improvement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2212/00—Indexing scheme relating to accessing, addressing or allocation within memory systems or architectures
- G06F2212/10—Providing a specific technical effect
- G06F2212/1032—Reliability improvement, data loss prevention, degraded operation etc
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2212/00—Indexing scheme relating to accessing, addressing or allocation within memory systems or architectures
- G06F2212/72—Details relating to flash memory management
- G06F2212/7201—Logical to physical mapping or translation of blocks or pages
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03M—CODING; DECODING; CODE CONVERSION IN GENERAL
- H03M13/00—Coding, decoding or code conversion, for error detection or error correction; Coding theory basic assumptions; Coding bounds; Error probability evaluation methods; Channel models; Simulation or testing of codes
- H03M13/03—Error detection or forward error correction by redundancy in data representation, i.e. code words containing more digits than the source words
- H03M13/05—Error detection or forward error correction by redundancy in data representation, i.e. code words containing more digits than the source words using block codes, i.e. a predetermined number of check bits joined to a predetermined number of information bits
- H03M13/13—Linear codes
- H03M13/15—Cyclic codes, i.e. cyclic shifts of codewords produce other codewords, e.g. codes defined by a generator polynomial, Bose-Chaudhuri-Hocquenghem [BCH] codes
- H03M13/151—Cyclic codes, i.e. cyclic shifts of codewords produce other codewords, e.g. codes defined by a generator polynomial, Bose-Chaudhuri-Hocquenghem [BCH] codes using error location or error correction polynomials
- H03M13/1515—Reed-Solomon codes
Definitions
- This patent document relates to error detection and correction in the context of a memory system.
- an error correction code (ECC) circuit is used to detect and correct an error which occurs in a memory cell and an error which occurs while data are transferred during read and write operations of a memory system.
- Various embodiments are directed to a memory system capable of improving error detection and error correction efficiency of the memory system, and a method of operating such a memory system.
- a memory system may include: a first error detection circuit suitable for generating a first error detection code using host data and a host address which are transferred from a host; a second error detection circuit suitable for generating a second error detection code using system data including one or more host data, a logical address corresponding to one or more host addresses, a physical address corresponding to the logical address and one or more first error detection codes; a third error detection code suitable for generating a third error detection code using the system data, the one or more first error detection codes and the second error detection code; and a first memory suitable for storing the system data, the one or more first error detection codes, the second error detection code and the third error detection code.
- a memory system may include: an error detection circuit suitable for generating an error detection code using an address and data during a write operation; and a memory suitable for storing the data and the error detection code during the write operation.
- an operation method of a memory system may include: receiving write data and a write address; generating an error detection code using the write data and the write address; and writing the write data and the error detection code to a region selected by the write address in a memory.
- FIG. 1 is a diagram illustrating a memory system in accordance with an embodiment.
- FIG. 2 is a diagram illustrating an operation of a memory system in accordance with an embodiment.
- FIG. 3 is a diagram illustrating a memory system in accordance with an embodiment.
- FIG. 4 is a diagram illustrating a write operation of a memory system in accordance with an embodiment.
- FIG. 5 is a diagram illustrating a read operation of a memory system in accordance with an embodiment.
- FIG. 6 is a diagram illustrating information protected by codes CRC- 3 , CRC- 10 and RS in accordance with an embodiment.
- FIG. 1 is a diagram illustrating a memory system 100 in accordance with an embodiment.
- the memory system 100 may include an error detection circuit 110 and a memory 120 . It is noted that FIG. 1 illustrates only a portion of the memory system 100 , which is directly related to error detection. Those skilled in the art will understand that the memory system 100 includes other components.
- an address ADD and data DATA with a write request REQ may be transferred to the memory system 100 from a host.
- the error detection circuit 110 may generate an error detection code CRC using the data DATA and the address ADD which are transferred from the host.
- CRC cyclic redundancy check
- codes based on algorithms other than the CRC may also be used.
- reference numeral 201 may represent the data DATA, the address ADD and the error detection code CRC which is generated by using the data DATA and the address ADD.
- the information represented by reference numeral 201 of FIG. 2 in which the data DATA and the address ADD are included in a box represented by CRC, may indicate that the data DATA and the address ADD are covered by the error detection code CRC.
- reference numeral 203 may represent the data DATA and the error detection code CRC which are stored in the memory 120 .
- Reference numeral 203 of FIG. 2 may indicate that the address ADD is excluded from the information represented by reference numeral 201 .
- the address ADD with a read request REQ may be transferred to the memory system 100 from the host.
- the data DATA and the error detection code CRC may be read from the region selected by the address ADD in the memory 120 .
- reference numeral 205 may represent that the address ADD transferred from the host is added to the data DATA and the error detection code CRC which are read from the memory 120 .
- the error detection circuit 110 may add the address ADD transferred from the host to the data DATA and the error detection code CRC which are read from the memory 120 , and detect errors of the read data DATA and the address ADD transferred from the host, using the error detection code CRC.
- the error detection circuit 110 may also perform an operation of correcting the detected errors.
- the data DATA read from the memory 120 included in the memory system 100 may be transferred to the host. Furthermore, when an error is detected by the error detection circuit 110 , the error detection ERR may be reported to the host.
- the memory system 100 of FIG. 1 may detect an error of the address ADD as well as the data DATA because the address ADD as well as the data DATA is covered by the error detection code CRC. Furthermore, since the address ADD is not stored in the memory 120 while the address ADD is covered by the error detection code CRC, the capacity waste of the memory 120 may be prevented.
- the memory system 100 of FIG. 1 may be implemented with one or more integrated circuit chips.
- the memory system 100 may implemented with one chip such that the error detection circuit 110 and the memory 120 are included in the one chip, or the memory system 100 may implemented with two or more chips such that the error detection circuit 110 is included in a memory controller chip, and the memory 120 is included in a memory chip.
- FIG. 3 is a configuration diagram illustrating a memory system 300 in accordance with an embodiment.
- the memory system 300 may include a memory controller 310 , a first memory 350 and a second memory 360 .
- the memory controller 310 may control read and write operations of the first memory 350 according to a request of a host.
- the memory controller 310 may include a host interface 311 , a scheduler 313 , a mapping circuit 315 , a first memory interface 317 , a second memory interface 319 , a first error detection circuit 321 , a second error detection circuit 323 and a third error detection circuit 325 .
- the host interface 311 may serve as an interface between the memory controller 310 and the host. Through the host interface 311 , requests of the host and addresses and data corresponding to the requests may be received, and processing results of the requests may be transmitted to the host.
- the host interface may be one of various types of interfaces such as PCIe (PCI-EXPRESS), CCIX (Cache Coherent Interconnect for Accelerators) and DIMM (Dual In-Line Memory Module).
- the scheduler 313 may perform scheduling to raise the performance of the memory system 300 .
- the scheduler 313 may determine the order of requests to be processed by the first memory 350 , among the requests received from the host. If necessary, the scheduler 313 may schedule operations of the first memory 350 in a different order from the order in which the requests are received from the host, in order to improve the performance of the memory system 300 . For example, although the host requested a read operation before a write operation, the scheduler 313 may adjust the order of the operations such that the write operation is performed before the read operation.
- the mapping circuit 315 may perform a mapping operation between data of the host and data to be stored in the first memory 350 .
- the size of a data chuck or page of the host may be different from the size of a data chunk or page of the first memory 350 .
- the host may transmit/receive 512-bit data whenever one read or write operation is performed, and the first memory 350 may transmit/receive 1024-bit data whenever one read or write operation is performed.
- the mapping circuit 315 may perform a mapping operation between two data chunks of the host side and one data chunk of the first memory side.
- the mapping circuit 315 may perform a mapping operation between a logical address and a physical address for wear-leveling or the like.
- the first memory interface 317 may serve as an interface for communication between the memory controller 310 and the first memory 350
- the second memory interface 319 may serve as an interface for communication between the memory controller 310 and the second memory 360 .
- the first to third error detection circuits 321 , 323 and 325 may generate error detection codes during a write operation, and detect an error using the error detection codes during a read operation. Ranges covered by the first to third error detection circuits 321 , 323 and 325 may be different from one another, and the first to third error detection circuits 321 , 323 and 325 will be described below in detail with reference to FIGS. 4 and 5 .
- the first memory 350 may serve as a memory for storing write data provided by the host during a write operation, and providing data stored therein as read data during a read operation.
- the first memory 350 may be one of various types of memories such as a PCRAM, NAND Flash, STT-MRAM and DRAM.
- the second memory 360 may serve as a memory for storing a mapping table between a logical address and a physical address. Since the second memory 360 is a memory for storing the mapping table, the second memory 360 may have a smaller capacity than the first memory 350 . For example, when the first memory 350 is a large-capacity PCRAM, the second memory 360 may be a DRAM having a smaller capacity than the first memory.
- FIG. 4 is a diagram for describing a write operation of the memory system 300 .
- Reference numeral 401 of FIG. 4 may represent that the first error detection circuit 321 generates a first error detection code CRC- 3 using host data DATA, a poison bit P and a host address ADD which are transferred from the host. That is, the first error detection code CRC- 3 may be generated by using the host data DATA, the poison bit P and the host address ADD as a message.
- the host data DATA may have 512 bits.
- the poison bit P may be a bit that the host uses to indicate the reliability of the data DATA. For example, when the data DATA is highly likely to contain an error, the host may indicate the likelihood using the poison bit P.
- the host address ADD may have 40 bits.
- the first error detection code CRC- 3 may be an error detection code that the first error detection circuit 321 generates using the host data DATA, the poison bit P and the host address ADD.
- a CRC- 3 code may be exemplified as the first error detection code CRC- 3 .
- the first error detection code CRC- 3 may have three bits.
- the information represented by reference numeral 401 in which the data DATA, the poison bit P and the address ADD are included in a box represented by CRC- 3 , may indicate that the data DATA, the poison bit P and the address ADD are covered by the first error detection code CRC- 3 .
- Reference numeral 403 of FIG. 4 may represent that the second error detection circuit 323 generates a second error detection code CRC- 10 using system data DATA 0 and DATA 1 , poison bits P 0 and P 1 , first error detection codes CRC- 3 _ 0 and CRC- 3 _ 1 , a logical address LADD, a physical address PADD and meta data META.
- the system data DATA 0 and DATA 1 may indicate data including two host data. Since the present embodiment exemplifies that the chunk size of the first memory 350 is twice larger than the chuck size of the host, two host data may be included in the system data DATA 0 and DATA 1 .
- the number of host data included in the system data DATA 0 and DATA 1 may be changed depending on the chunk sizes of the host and the first memory 350 . Since the present embodiment exemplifies that the system data DATA 0 and DATA 1 include two host data, the system data may have 1024 bits. The system data DATA 0 and DATA 1 and the host data may be mapped by the mapping circuit 315 .
- the poison bits P 0 and P 1 may be poison bits which correspond to the two host data included in the system data DATA 0 and DATA 1 , respectively.
- the first error detection codes CRC- 3 _ 0 and CRC- 3 _ 1 may be error detection codes which correspond to the two host data included in the system data DATA 0 and DATA 1 , respectively.
- the logical address LADD may be a logical address corresponding to the system data DATA 0 and DATA 1 .
- the logical address LADD may be generated by the mapping circuit 315 using the host address ADD. Since the logical address LADD corresponds to data twice larger than the host address ADD, the logical address LADD may have 39 bits less by one bit than the host address ADD.
- the physical address PADD may be a physical address corresponding to the logical address. For a wear-leveling operation or the like, an address mapping operation between the logical address LADD and the physical address PADD may be performed.
- the physical address PADD may have a larger number of bits than the logical address LADD. For example, the physical address PADD may have 40 bits. This is because the number of regions corresponding to the physical address PADD needs to be larger than the number of regions corresponding to the logical address LADD, for a wear leveling operation, a bad block management operation and the like.
- the meta data META may be data which are operated for management of the first memory 350 .
- the meta data META may include write counter information, wear leveling pending bit information and write disturbance pending bit information for managing wear leveling, write disturbance and the like.
- the meta data META may have 27 bits, for example.
- the second error detection code CRC- 10 may be an error detection code that the second error detection circuit 323 generates using the system data DATA 0 and DATA 1 , the poison bits P 0 and P 1 , the first error detection codes CRC- 3 _ 0 and CRC- 3 _ 1 , the logical address LADD, the physical address PADD and the meta data META. That is, the second error detection code CRC- 10 may be generated by using the system data DATA 0 and DATA 1 , the poison bits P 0 and P 1 , the first error detection codes CRC- 3 _ 0 and CRC- 3 _ 1 , the logical address LADD, the physical address PADD and the meta data META as a message.
- a CRC- 10 code may be exemplified as the second error detection code CRC- 10 .
- the second error detection code CRC- 10 may have 10 bits.
- the system data DATA 0 and DATA 1 , the poison bits P 0 and P 1 , the first error detection codes CRC- 3 _ 0 and CRC- 3 _ 1 , the logical address LADD, the physical address PADD and the meta data META, which are included in a box represented by CRC- 10 in the information represented by reference numeral 403 may be covered by the second error detection code CRC- 10 .
- Reference numeral 403 may represent that the host address ADD which was present in the information represented by reference numeral 401 is excluded from the target covered by the second error detection code CRC- 10 , i.e. the message.
- Reference numeral 405 of FIG. 4 may represent information stored in the second memory 360 .
- the second memory 360 may store the mapping table indicating a mapping relationship between the logical address LADD and the physical address PADD.
- Reference numeral 407 of FIG. 4 may represent that the third error detection circuit 325 generates a third error detection code RS using the system data DATA 0 and DATA 1 , the poison bits P 0 and P 1 , the first error detection codes CRC- 3 _ 0 and CRC- 3 _ 1 , the meta data META and the second error detection code CRC- 10 . That is, the third error detection code RS may be generated by using the system data DATA 0 and DATA 1 , the poison bits P 0 and P 1 , the first error detection codes CRC- 3 _ 0 and CRC- 3 _ 1 , the meta data META and the second error detection code CRC- 10 as a message.
- Reference numeral 407 may represent that the logical address LADD and the physical address PADD are removed from the message of the third error detection code RS.
- a Reed-Solomon (RS) code may be exemplified as the third error detection code CRC- 10 .
- the third error detection code RS may have 320 bits.
- the system data DATA 0 and DATA 1 , the poison bits P 0 and P 1 , the first error detection codes CRC- 3 _ 0 and CRC- 3 _ 1 , the meta data META and the second error detection code CRC- 10 , which are included in a box represented by RS, may be covered by the third error detection code RS.
- Reference numeral 409 of FIG. 4 may represent information stored in the first memory 350 .
- Reference numeral 409 of FIG. 4 may represent the same information as reference numeral 407 . That is, both of the third error detection code RS and the message of the third error detection code RS may be stored in the first memory 350 .
- FIG. 5 is a diagram for describing a read operation of the memory system 300 .
- Reference numeral 409 of FIG. 5 may represent information stored in the first memory 350 .
- the information 409 stored in the first memory 350 may be read and transferred to the third error detection circuit 325 .
- a physical address PADD may be used.
- the physical address PADD may be generated through a process in which the mapping circuit 315 generates a logical address LADD using an address ADD transferred from the host with a read request, and maps the logical address LADD to the physical address PADD using the mapping table stored in the second memory 360 .
- Reference numeral 501 of FIG. 5 may represent information that the third error detection circuit 325 receives from the first memory 350 .
- the third error detection circuit 325 may detect errors of the system data DATA 0 and DATA 1 , the poison bits P 0 and P 1 , the first error detection codes CRC- 3 _ 0 and CRC- 3 _ 1 , the meta data META and the second error detection code CRC- 10 using the third error detection code RS included in the information 501 , and correct the detected errors.
- the third error detection circuit 325 may transfer the system data DATA 0 and DATA 1 , the poison bits P 0 and P 1 , the first error detection codes CRC- 3 _ 0 and CRC- 3 _ 1 , the meta data META and the second error detection code CRC- 10 , of which the errors are corrected, to the second error detection circuit 323 .
- Reference numeral 503 of FIG. 5 may represent information that the second error detection circuit 323 receives from the third error detection circuit 325 and the mapping circuit 315 .
- the second error detection circuit 323 may receive the system data DATA 0 and DATA 1 , the poison bits P 0 and P 1 , the first error detection codes CRC- 3 _ 0 and CRC- 3 _ 1 , the meta data META and the second error detection code CRC- 10 from the third error detection circuit 325 , and receive the logical address LADD and the physical address PADD from the mapping circuit 315 .
- the second error detection circuit 323 may detect errors of the system data DATA 0 and DATA 1 , the poison bits P 0 and P 1 , the first error detection codes CRC- 3 _ 0 and CRC- 3 _ 1 , the meta data META, the logical address LADD and the physical address PADD using the second error detection code CRC- 10 .
- the second error detection circuit 323 may inform the host that the errors are detected, through the host interface 311 .
- the present embodiment may exemplify that the second error detection code CRC- 10 includes information for detecting an error. However, when the second error detection code CRC- 10 includes information for correcting a detected error as well as the information for detecting an error, the second error detection circuit 323 may correct the detected error.
- the second error detection circuit 323 may transfer a part of the system data DATA 0 and DATA 1 , a part of the poison bits P 0 and P 1 and a part of the first error detection codes CRC- 3 _ 0 and CRC- 3 _ 1 to the first error detection circuit 321 .
- the parts of the system data DATA 0 and DATA 1 , the poison bits P 0 and P 1 and the first error detection codes CRC- 3 _ 0 and CRC- 3 _ 1 may indicate parts corresponding to the host address ADD among the system data DATA 0 and DATA 1 , the poison bits P 0 and P 1 and the first error detection codes CRC- 3 _ 0 and CRC- 3 _ 1 .
- Reference numeral 505 of FIG. 5 may represent the information DATA, P and CRC- 3 that the first error detection circuit 321 receives from the second error detection circuit 323 and the host address ADD that the first error detection circuit 321 receives from the host.
- the first error detection circuit 321 may detect errors of the data DATA, the poison bit P and the host address ADD using the first error detection code CRC- 3 .
- the first error detection circuit 321 may inform the host that the errors are detected, through the host interface 311 .
- the present embodiment may exemplify that the first error detection code CRC- 3 includes information for detecting an error.
- the first error detection circuit 321 may correct the detected error. After the error is detected by the first error detection circuit 321 , the data DATA and the poison bit P may be transferred to the host through the host interface 311 .
- the first error detection circuit 321 may encode/decode the first error detection code CRC- 3 at the point where the data DATA, the poison bit P and the address ADD are transferred to the memory controller from the host. Therefore, the first error detection circuit 321 may detect errors of the data DATA, the poison bit P and the address ADD, which occur throughout the memory system.
- the second error detection circuit 323 may encode/decode the second error detection code CRC- 10 for detecting errors of the system data DATA 0 and DATA 1 , the poison bits P 0 and P 1 , the first error detection codes CRC- 3 _ 0 and CRC- 3 _ 1 , the meta data META, the logical address LADD and the physical address PADD. Therefore, the second error detection circuit 323 may detect not only an error which occurs in the first memory 350 , but also an error which occurs in the second memory 360 .
- the third error detection circuit 325 may perform an operation of detecting and correcting errors of the information DATA 0 , DATA 1 , P 0 , P 1 , CRC- 3 _ 0 , CRC- 3 _ 1 , META and CRC- 10 stored in the first memory 350 . Therefore, an error which occurs in the first memory 350 may be reliably detected and corrected.
- first and second error detection circuits 321 and 323 include the addresses ADD ⁇ LADD and PADD in the error detection target, such addresses may not be stored in the first memory 350 , which makes it possible to prevent capacity waste of the first memory 350 .
- FIG. 6 is a diagram illustrating information protected by the codes CRC- 3 , CRC- 10 and RS.
- FIG. 6 illustrates that the system data DATA 0 and DATA 1 , the poison bits P 0 and P 1 and addresses ADD 0 and ADD 1 are protected by the first error detection codes CRC- 3 _ 0 and CRC- 3 _ 1 . Therefore, the system data DATA 0 and DATA 1 , the poison bits P 0 and P 1 and the addresses ADD 0 and ADD 1 which are transferred to the memory controller 310 from the host may be protected, and errors of the system data DATA 0 and DATA 1 and the poison bits P 0 and P 1 which are transferred to the host from the memory controller 310 may be detected and corrected.
- the information which has been protected by the first error detection codes CRC- 3 _ 0 and CRC- 3 _ 1 may be redundantly protected by the second error detection code CRC- 10 .
- the information such as the meta data META, the logical address LADD and the physical address PADD, which the memory controller 310 additionally uses to process data and addresses of the memory system 300 , may be further protected.
- the information which has been protected by the first error detection codes CRC- 3 _ 0 and CRC- 3 _ 1 and the second error detection code CRC- 10 may be redundantly protected by the third error detection code RS, and an error which occurs during the process in which the information is inputted to/outputted from the first memory 350 and the process in which the information is stored in the first memory 350 may be detected and corrected by the third error detection code RS.
- the information processed by the memory controller 310 , the first memory 350 and the second memory 360 of the memory system 300 is redundantly protected by the three kinds of codes CRC- 3 _ 0 , CRC- 3 _ 1 , CRC- 10 and RS, an error which is not detected or corrected by one code may be detected and corrected by another code.
- an error which occurred in the first memory 350 and is not corrected by the third error detection code RS may be corrected by the second error detection code CRC- 10 .
- the three kinds of codes CRC- 3 _ 0 , CRC- 3 _ 1 , CRC- 10 and RS cover errors in different ranges which overlap one another, an error can be detected and corrected even though the error occurs at any position of the memory system 300 .
- the error detection and error correction efficiency of the memory system can be improved.
Abstract
Description
- This application claims priority under 35 U.S.C. § 119 to Korean Patent Application No. 10-2019-0009054, filed on Jan. 24, 2019, which is incorporated herein by reference in its entirety.
- This patent document relates to error detection and correction in the context of a memory system.
- In the beginning of the semiconductor memory device industry, a number of original good dies with no defective memory cells present in a memory chip passed through a semiconductor fabrication process. The good dies were spread over a wafer. However, the gradual increase in capacities of memory devices has made it difficult to fabricate a memory device having no defective memory cells. At present, it seems very unlikely that such a defect-free memory device will be fabricated in the near future. As one measure for overcoming such a situation, a method for repairing defective memory cells of a memory device with redundancy memory cells is used.
- As another measure, an error correction code (ECC) circuit is used to detect and correct an error which occurs in a memory cell and an error which occurs while data are transferred during read and write operations of a memory system.
- Recently, as a modern memory system grows more complex, a memory controller of such system also performs various processes on addresses and data, which may lead to additional errors. Thus, there is a demand for a technique for detecting and correcting errors that occur in the memory controller as well as in the memory of the memory system.
- Various embodiments are directed to a memory system capable of improving error detection and error correction efficiency of the memory system, and a method of operating such a memory system.
- In an embodiment, a memory system may include: a first error detection circuit suitable for generating a first error detection code using host data and a host address which are transferred from a host; a second error detection circuit suitable for generating a second error detection code using system data including one or more host data, a logical address corresponding to one or more host addresses, a physical address corresponding to the logical address and one or more first error detection codes; a third error detection code suitable for generating a third error detection code using the system data, the one or more first error detection codes and the second error detection code; and a first memory suitable for storing the system data, the one or more first error detection codes, the second error detection code and the third error detection code.
- In an embodiment, a memory system may include: an error detection circuit suitable for generating an error detection code using an address and data during a write operation; and a memory suitable for storing the data and the error detection code during the write operation.
- In an embodiment, an operation method of a memory system may include: receiving write data and a write address; generating an error detection code using the write data and the write address; and writing the write data and the error detection code to a region selected by the write address in a memory.
-
FIG. 1 is a diagram illustrating a memory system in accordance with an embodiment. -
FIG. 2 is a diagram illustrating an operation of a memory system in accordance with an embodiment. -
FIG. 3 is a diagram illustrating a memory system in accordance with an embodiment. -
FIG. 4 is a diagram illustrating a write operation of a memory system in accordance with an embodiment. -
FIG. 5 is a diagram illustrating a read operation of a memory system in accordance with an embodiment. -
FIG. 6 is a diagram illustrating information protected by codes CRC-3, CRC-10 and RS in accordance with an embodiment. - Various embodiments of the present invention are described below in more detail with reference to the accompanying drawings. The present invention may, however, be embodied in other forms and thus should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure is thorough and complete and fully conveys the scope of the present invention to those skilled in the art. Throughout the disclosure, like reference numerals refer to like parts throughout the various figures and embodiments of the present invention. Also, throughout the specification, reference to “an embodiment,” “another embodiment” or the like is not necessarily to the same embodiment, and different references to any such phrase are not necessarily to the same embodiment(s).
-
FIG. 1 is a diagram illustrating amemory system 100 in accordance with an embodiment. - Referring to
FIG. 1 , thememory system 100 may include anerror detection circuit 110 and amemory 120. It is noted thatFIG. 1 illustrates only a portion of thememory system 100, which is directly related to error detection. Those skilled in the art will understand that thememory system 100 includes other components. - During a write operation, an address ADD and data DATA with a write request REQ may be transferred to the
memory system 100 from a host. - During the write operation, the
error detection circuit 110 may generate an error detection code CRC using the data DATA and the address ADD which are transferred from the host. In the present embodiment, although a cyclic redundancy check (CRC) code is exemplified as the error detection code CRC, codes based on algorithms other than the CRC may also be used. InFIG. 2 ,reference numeral 201 may represent the data DATA, the address ADD and the error detection code CRC which is generated by using the data DATA and the address ADD. The information represented byreference numeral 201 ofFIG. 2 , in which the data DATA and the address ADD are included in a box represented by CRC, may indicate that the data DATA and the address ADD are covered by the error detection code CRC. - During the write operation, the data DATA and the error detection code CRC may be written to a region selected by the address ADD in the
memory 120. InFIG. 2 ,reference numeral 203 may represent the data DATA and the error detection code CRC which are stored in thememory 120.Reference numeral 203 ofFIG. 2 may indicate that the address ADD is excluded from the information represented byreference numeral 201. - During a read operation, the address ADD with a read request REQ may be transferred to the
memory system 100 from the host. - During the read operation, the data DATA and the error detection code CRC may be read from the region selected by the address ADD in the
memory 120. InFIG. 2 ,reference numeral 205 may represent that the address ADD transferred from the host is added to the data DATA and the error detection code CRC which are read from thememory 120. - During the read operation, the
error detection circuit 110 may add the address ADD transferred from the host to the data DATA and the error detection code CRC which are read from thememory 120, and detect errors of the read data DATA and the address ADD transferred from the host, using the error detection code CRC. When the error detection code CRC includes information enough to correct the detected errors as well as information for detecting the errors, theerror detection circuit 110 may also perform an operation of correcting the detected errors. - The data DATA read from the
memory 120 included in thememory system 100 may be transferred to the host. Furthermore, when an error is detected by theerror detection circuit 110, the error detection ERR may be reported to the host. - The
memory system 100 ofFIG. 1 may detect an error of the address ADD as well as the data DATA because the address ADD as well as the data DATA is covered by the error detection code CRC. Furthermore, since the address ADD is not stored in thememory 120 while the address ADD is covered by the error detection code CRC, the capacity waste of thememory 120 may be prevented. - The
memory system 100 ofFIG. 1 may be implemented with one or more integrated circuit chips. For example, thememory system 100 may implemented with one chip such that theerror detection circuit 110 and thememory 120 are included in the one chip, or thememory system 100 may implemented with two or more chips such that theerror detection circuit 110 is included in a memory controller chip, and thememory 120 is included in a memory chip. -
FIG. 3 is a configuration diagram illustrating amemory system 300 in accordance with an embodiment. - Referring to
FIG. 3 , thememory system 300 may include amemory controller 310, afirst memory 350 and asecond memory 360. - The
memory controller 310 may control read and write operations of thefirst memory 350 according to a request of a host. - The
memory controller 310 may include ahost interface 311, ascheduler 313, amapping circuit 315, afirst memory interface 317, asecond memory interface 319, a firsterror detection circuit 321, a seconderror detection circuit 323 and a thirderror detection circuit 325. - The
host interface 311 may serve as an interface between thememory controller 310 and the host. Through thehost interface 311, requests of the host and addresses and data corresponding to the requests may be received, and processing results of the requests may be transmitted to the host. The host interface may be one of various types of interfaces such as PCIe (PCI-EXPRESS), CCIX (Cache Coherent Interconnect for Accelerators) and DIMM (Dual In-Line Memory Module). - The
scheduler 313 may perform scheduling to raise the performance of thememory system 300. For example, thescheduler 313 may determine the order of requests to be processed by thefirst memory 350, among the requests received from the host. If necessary, thescheduler 313 may schedule operations of thefirst memory 350 in a different order from the order in which the requests are received from the host, in order to improve the performance of thememory system 300. For example, although the host requested a read operation before a write operation, thescheduler 313 may adjust the order of the operations such that the write operation is performed before the read operation. - The
mapping circuit 315 may perform a mapping operation between data of the host and data to be stored in thefirst memory 350. The size of a data chuck or page of the host may be different from the size of a data chunk or page of thefirst memory 350. For example, the host may transmit/receive 512-bit data whenever one read or write operation is performed, and thefirst memory 350 may transmit/receive 1024-bit data whenever one read or write operation is performed. Themapping circuit 315 may perform a mapping operation between two data chunks of the host side and one data chunk of the first memory side. Furthermore, themapping circuit 315 may perform a mapping operation between a logical address and a physical address for wear-leveling or the like. - The
first memory interface 317 may serve as an interface for communication between thememory controller 310 and thefirst memory 350, and thesecond memory interface 319 may serve as an interface for communication between thememory controller 310 and thesecond memory 360. - The first to third
error detection circuits error detection circuits error detection circuits FIGS. 4 and 5 . - The
first memory 350 may serve as a memory for storing write data provided by the host during a write operation, and providing data stored therein as read data during a read operation. Thefirst memory 350 may be one of various types of memories such as a PCRAM, NAND Flash, STT-MRAM and DRAM. - The
second memory 360 may serve as a memory for storing a mapping table between a logical address and a physical address. Since thesecond memory 360 is a memory for storing the mapping table, thesecond memory 360 may have a smaller capacity than thefirst memory 350. For example, when thefirst memory 350 is a large-capacity PCRAM, thesecond memory 360 may be a DRAM having a smaller capacity than the first memory. -
FIG. 4 is a diagram for describing a write operation of thememory system 300. -
Reference numeral 401 ofFIG. 4 may represent that the firsterror detection circuit 321 generates a first error detection code CRC-3 using host data DATA, a poison bit P and a host address ADD which are transferred from the host. That is, the first error detection code CRC-3 may be generated by using the host data DATA, the poison bit P and the host address ADD as a message. The host data DATA may have 512 bits. The poison bit P may be a bit that the host uses to indicate the reliability of the data DATA. For example, when the data DATA is highly likely to contain an error, the host may indicate the likelihood using the poison bit P. The host address ADD may have 40 bits. The first error detection code CRC-3 may be an error detection code that the firsterror detection circuit 321 generates using the host data DATA, the poison bit P and the host address ADD. In the present embodiment, a CRC-3 code may be exemplified as the first error detection code CRC-3. In this case, the first error detection code CRC-3 may have three bits. The information represented byreference numeral 401, in which the data DATA, the poison bit P and the address ADD are included in a box represented by CRC-3, may indicate that the data DATA, the poison bit P and the address ADD are covered by the first error detection code CRC-3. -
Reference numeral 403 ofFIG. 4 may represent that the seconderror detection circuit 323 generates a second error detection code CRC-10 using system data DATA0 and DATA1, poison bits P0 and P1, first error detection codes CRC-3_0 and CRC-3_1, a logical address LADD, a physical address PADD and meta data META. The system data DATA0 and DATA1 may indicate data including two host data. Since the present embodiment exemplifies that the chunk size of thefirst memory 350 is twice larger than the chuck size of the host, two host data may be included in the system data DATA0 and DATA1. However, the number of host data included in the system data DATA0 and DATA1 may be changed depending on the chunk sizes of the host and thefirst memory 350. Since the present embodiment exemplifies that the system data DATA0 and DATA1 include two host data, the system data may have 1024 bits. The system data DATA0 and DATA1 and the host data may be mapped by themapping circuit 315. - The poison bits P0 and P1 may be poison bits which correspond to the two host data included in the system data DATA0 and DATA1, respectively. The first error detection codes CRC-3_0 and CRC-3_1 may be error detection codes which correspond to the two host data included in the system data DATA0 and DATA1, respectively. The logical address LADD may be a logical address corresponding to the system data DATA0 and DATA1. The logical address LADD may be generated by the
mapping circuit 315 using the host address ADD. Since the logical address LADD corresponds to data twice larger than the host address ADD, the logical address LADD may have 39 bits less by one bit than the host address ADD. The physical address PADD may be a physical address corresponding to the logical address. For a wear-leveling operation or the like, an address mapping operation between the logical address LADD and the physical address PADD may be performed. The physical address PADD may have a larger number of bits than the logical address LADD. For example, the physical address PADD may have 40 bits. This is because the number of regions corresponding to the physical address PADD needs to be larger than the number of regions corresponding to the logical address LADD, for a wear leveling operation, a bad block management operation and the like. The meta data META may be data which are operated for management of thefirst memory 350. The meta data META may include write counter information, wear leveling pending bit information and write disturbance pending bit information for managing wear leveling, write disturbance and the like. The meta data META may have 27 bits, for example. - The second error detection code CRC-10 may be an error detection code that the second
error detection circuit 323 generates using the system data DATA0 and DATA1, the poison bits P0 and P1, the first error detection codes CRC-3_0 and CRC-3_1, the logical address LADD, the physical address PADD and the meta data META. That is, the second error detection code CRC-10 may be generated by using the system data DATA0 and DATA1, the poison bits P0 and P1, the first error detection codes CRC-3_0 and CRC-3_1, the logical address LADD, the physical address PADD and the meta data META as a message. In the present embodiment, a CRC-10 code may be exemplified as the second error detection code CRC-10. In this case, the second error detection code CRC-10 may have 10 bits. The system data DATA0 and DATA1, the poison bits P0 and P1, the first error detection codes CRC-3_0 and CRC-3_1, the logical address LADD, the physical address PADD and the meta data META, which are included in a box represented by CRC-10 in the information represented byreference numeral 403, may be covered by the second error detection code CRC-10.Reference numeral 403 may represent that the host address ADD which was present in the information represented byreference numeral 401 is excluded from the target covered by the second error detection code CRC-10, i.e. the message. -
Reference numeral 405 ofFIG. 4 may represent information stored in thesecond memory 360. Thesecond memory 360 may store the mapping table indicating a mapping relationship between the logical address LADD and the physical address PADD. -
Reference numeral 407 ofFIG. 4 may represent that the thirderror detection circuit 325 generates a third error detection code RS using the system data DATA0 and DATA1, the poison bits P0 and P1, the first error detection codes CRC-3_0 and CRC-3_1, the meta data META and the second error detection code CRC-10. That is, the third error detection code RS may be generated by using the system data DATA0 and DATA1, the poison bits P0 and P1, the first error detection codes CRC-3_0 and CRC-3_1, the meta data META and the second error detection code CRC-10 as a message.Reference numeral 407 may represent that the logical address LADD and the physical address PADD are removed from the message of the third error detection code RS. In the present embodiment, a Reed-Solomon (RS) code may be exemplified as the third error detection code CRC-10. In this case, the third error detection code RS may have 320 bits. The system data DATA0 and DATA1, the poison bits P0 and P1, the first error detection codes CRC-3_0 and CRC-3_1, the meta data META and the second error detection code CRC-10, which are included in a box represented by RS, may be covered by the third error detection code RS. -
Reference numeral 409 ofFIG. 4 may represent information stored in thefirst memory 350.Reference numeral 409 ofFIG. 4 may represent the same information asreference numeral 407. That is, both of the third error detection code RS and the message of the third error detection code RS may be stored in thefirst memory 350. -
FIG. 5 is a diagram for describing a read operation of thememory system 300. -
Reference numeral 409 ofFIG. 5 may represent information stored in thefirst memory 350. Theinformation 409 stored in thefirst memory 350 may be read and transferred to the thirderror detection circuit 325. - In order to access the
first memory 350, a physical address PADD may be used. The physical address PADD may be generated through a process in which themapping circuit 315 generates a logical address LADD using an address ADD transferred from the host with a read request, and maps the logical address LADD to the physical address PADD using the mapping table stored in thesecond memory 360. -
Reference numeral 501 ofFIG. 5 may represent information that the thirderror detection circuit 325 receives from thefirst memory 350. The thirderror detection circuit 325 may detect errors of the system data DATA0 and DATA1, the poison bits P0 and P1, the first error detection codes CRC-3_0 and CRC-3_1, the meta data META and the second error detection code CRC-10 using the third error detection code RS included in theinformation 501, and correct the detected errors. The thirderror detection circuit 325 may transfer the system data DATA0 and DATA1, the poison bits P0 and P1, the first error detection codes CRC-3_0 and CRC-3_1, the meta data META and the second error detection code CRC-10, of which the errors are corrected, to the seconderror detection circuit 323. -
Reference numeral 503 ofFIG. 5 may represent information that the seconderror detection circuit 323 receives from the thirderror detection circuit 325 and themapping circuit 315. The seconderror detection circuit 323 may receive the system data DATA0 and DATA1, the poison bits P0 and P1, the first error detection codes CRC-3_0 and CRC-3_1, the meta data META and the second error detection code CRC-10 from the thirderror detection circuit 325, and receive the logical address LADD and the physical address PADD from themapping circuit 315. The seconderror detection circuit 323 may detect errors of the system data DATA0 and DATA1, the poison bits P0 and P1, the first error detection codes CRC-3_0 and CRC-3_1, the meta data META, the logical address LADD and the physical address PADD using the second error detection code CRC-10. When the errors are detected, the seconderror detection circuit 323 may inform the host that the errors are detected, through thehost interface 311. The present embodiment may exemplify that the second error detection code CRC-10 includes information for detecting an error. However, when the second error detection code CRC-10 includes information for correcting a detected error as well as the information for detecting an error, the seconderror detection circuit 323 may correct the detected error. The seconderror detection circuit 323 may transfer a part of the system data DATA0 and DATA1, a part of the poison bits P0 and P1 and a part of the first error detection codes CRC-3_0 and CRC-3_1 to the firsterror detection circuit 321. The parts of the system data DATA0 and DATA1, the poison bits P0 and P1 and the first error detection codes CRC-3_0 and CRC-3_1 may indicate parts corresponding to the host address ADD among the system data DATA0 and DATA1, the poison bits P0 and P1 and the first error detection codes CRC-3_0 and CRC-3_1. -
Reference numeral 505 ofFIG. 5 may represent the information DATA, P and CRC-3 that the firsterror detection circuit 321 receives from the seconderror detection circuit 323 and the host address ADD that the firsterror detection circuit 321 receives from the host. The firsterror detection circuit 321 may detect errors of the data DATA, the poison bit P and the host address ADD using the first error detection code CRC-3. When the errors are detected, the firsterror detection circuit 321 may inform the host that the errors are detected, through thehost interface 311. The present embodiment may exemplify that the first error detection code CRC-3 includes information for detecting an error. However, when the first error detection code CRC-3 includes information for correcting a detected error as well as the information for detecting an error, the firsterror detection circuit 321 may correct the detected error. After the error is detected by the firsterror detection circuit 321, the data DATA and the poison bit P may be transferred to the host through thehost interface 311. - Referring to
FIGS. 3 to 5 , the firsterror detection circuit 321 may encode/decode the first error detection code CRC-3 at the point where the data DATA, the poison bit P and the address ADD are transferred to the memory controller from the host. Therefore, the firsterror detection circuit 321 may detect errors of the data DATA, the poison bit P and the address ADD, which occur throughout the memory system. - The second
error detection circuit 323 may encode/decode the second error detection code CRC-10 for detecting errors of the system data DATA0 and DATA1, the poison bits P0 and P1, the first error detection codes CRC-3_0 and CRC-3_1, the meta data META, the logical address LADD and the physical address PADD. Therefore, the seconderror detection circuit 323 may detect not only an error which occurs in thefirst memory 350, but also an error which occurs in thesecond memory 360. - The third
error detection circuit 325 may perform an operation of detecting and correcting errors of the information DATA0, DATA1, P0, P1, CRC-3_0, CRC-3_1, META and CRC-10 stored in thefirst memory 350. Therefore, an error which occurs in thefirst memory 350 may be reliably detected and corrected. - Although the first and second
error detection circuits first memory 350, which makes it possible to prevent capacity waste of thefirst memory 350. -
FIG. 6 is a diagram illustrating information protected by the codes CRC-3, CRC-10 and RS. -
FIG. 6 illustrates that the system data DATA0 and DATA1, the poison bits P0 and P1 and addresses ADD0 and ADD1 are protected by the first error detection codes CRC-3_0 and CRC-3_1. Therefore, the system data DATA0 and DATA1, the poison bits P0 and P1 and the addresses ADD0 and ADD1 which are transferred to thememory controller 310 from the host may be protected, and errors of the system data DATA0 and DATA1 and the poison bits P0 and P1 which are transferred to the host from thememory controller 310 may be detected and corrected. - The information which has been protected by the first error detection codes CRC-3_0 and CRC-3_1 may be redundantly protected by the second error detection code CRC-10. In addition, the information such as the meta data META, the logical address LADD and the physical address PADD, which the
memory controller 310 additionally uses to process data and addresses of thememory system 300, may be further protected. - The information which has been protected by the first error detection codes CRC-3_0 and CRC-3_1 and the second error detection code CRC-10 may be redundantly protected by the third error detection code RS, and an error which occurs during the process in which the information is inputted to/outputted from the
first memory 350 and the process in which the information is stored in thefirst memory 350 may be detected and corrected by the third error detection code RS. - Since the information processed by the
memory controller 310, thefirst memory 350 and thesecond memory 360 of thememory system 300 is redundantly protected by the three kinds of codes CRC-3_0, CRC-3_1, CRC-10 and RS, an error which is not detected or corrected by one code may be detected and corrected by another code. For example, an error which occurred in thefirst memory 350 and is not corrected by the third error detection code RS may be corrected by the second error detection code CRC-10. Furthermore, since the three kinds of codes CRC-3_0, CRC-3_1, CRC-10 and RS cover errors in different ranges which overlap one another, an error can be detected and corrected even though the error occurs at any position of thememory system 300. - In accordance with various embodiments, the error detection and error correction efficiency of the memory system can be improved.
- Although various embodiments have been illustrated and described, it will be apparent to those skilled in the art in light of the present disclosure that various changes and modifications may be made without departing from the spirit and scope of the invention as defined in the following claims.
Claims (16)
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020190009054A KR20200092036A (en) | 2019-01-24 | 2019-01-24 | Memory system and operation method of memory system |
KR10-2019-0009054 | 2019-01-24 |
Publications (2)
Publication Number | Publication Date |
---|---|
US20200241958A1 true US20200241958A1 (en) | 2020-07-30 |
US11216335B2 US11216335B2 (en) | 2022-01-04 |
Family
ID=71733704
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/683,989 Active 2040-03-12 US11216335B2 (en) | 2019-01-24 | 2019-11-14 | Memory system and operation method thereof |
Country Status (4)
Country | Link |
---|---|
US (1) | US11216335B2 (en) |
KR (1) | KR20200092036A (en) |
CN (1) | CN111475327B (en) |
TW (1) | TW202029209A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2022125521A1 (en) * | 2020-12-09 | 2022-06-16 | Micron Technology, Inc. | Modified parity data using a poison data unit |
WO2022125372A1 (en) * | 2020-12-09 | 2022-06-16 | Micron Technology, Inc. | Modified checksum using a poison data pattern |
US20220413763A1 (en) * | 2021-06-24 | 2022-12-29 | Phison Electronics Corp. | Mapping information management method, memory storage device and memory control circuit unit |
US11819504B2 (en) | 2018-08-26 | 2023-11-21 | Attain Health Inc. | Methods and compositions to increase hair growth and/or prevent hair loss |
Family Cites Families (37)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CA2002361C (en) * | 1989-03-10 | 1993-12-21 | Robert M. Blake | Fault tolerant computer memory systems and components employing dual level error correction and detection with disablement feature |
US5864440A (en) * | 1994-12-27 | 1999-01-26 | International Business Machines Corporation | Data processing method and data storage system |
US5761221A (en) * | 1995-12-11 | 1998-06-02 | International Business Machines Corporation | Memory implemented error detection and correction code using memory modules |
JPH10198608A (en) * | 1997-01-08 | 1998-07-31 | Mitsubishi Electric Corp | Memory card |
JP3230485B2 (en) * | 1998-04-09 | 2001-11-19 | 日本電気株式会社 | One-chip microcomputer |
US6457067B1 (en) * | 1998-12-18 | 2002-09-24 | Unisys Corporation | System and method for detecting faults in storage device addressing logic |
US6941505B2 (en) * | 2000-09-12 | 2005-09-06 | Hitachi, Ltd. | Data processing system and data processing method |
US20070079212A1 (en) * | 2005-04-01 | 2007-04-05 | Silverback Systems, Inc. | Techniques for efficient error correction code implementation in a system |
JP4734033B2 (en) * | 2005-05-30 | 2011-07-27 | 株式会社東芝 | Storage device |
US8468416B2 (en) * | 2007-06-26 | 2013-06-18 | International Business Machines Corporation | Combined group ECC protection and subgroup parity protection |
US8136010B2 (en) * | 2007-12-21 | 2012-03-13 | International Business Machines Corporation | Apparatus for pipelined cyclic redundancy check circuit with multiple intermediate outputs |
CN101882119B (en) * | 2009-05-08 | 2014-05-14 | 上海炬力集成电路设计有限公司 | NAND flash memory controller and data transmission method thereof |
JP5574230B2 (en) * | 2010-04-28 | 2014-08-20 | 株式会社日立製作所 | Fault handling method and computer |
US8308223B2 (en) * | 2010-08-03 | 2012-11-13 | Honda Motor Company, Ltd. | Net structure for a vehicle |
US8990660B2 (en) * | 2010-09-13 | 2015-03-24 | Freescale Semiconductor, Inc. | Data processing system having end-to-end error correction and method therefor |
US8566672B2 (en) * | 2011-03-22 | 2013-10-22 | Freescale Semiconductor, Inc. | Selective checkbit modification for error correction |
US8607121B2 (en) * | 2011-04-29 | 2013-12-10 | Freescale Semiconductor, Inc. | Selective error detection and error correction for a memory interface |
US8990657B2 (en) * | 2011-06-14 | 2015-03-24 | Freescale Semiconductor, Inc. | Selective masking for error correction |
US8949694B2 (en) * | 2011-09-23 | 2015-02-03 | International Business Machines Corporation | Address error detection |
US9189329B1 (en) * | 2011-10-13 | 2015-11-17 | Marvell International Ltd. | Generating error correcting code (ECC) data using an ECC corresponding to an identified ECC protection level |
JP2013137708A (en) * | 2011-12-28 | 2013-07-11 | Toshiba Corp | Memory controller, data storage device, and memory control method |
KR102204391B1 (en) | 2014-08-18 | 2021-01-18 | 삼성전자주식회사 | Memory device having sharable ECC (Error Correction Code) cell array |
KR20160021558A (en) | 2014-08-18 | 2016-02-26 | 삼성전자주식회사 | Driving method of ultrasonic transducer, and ultrasonic apparatus |
TWI566096B (en) * | 2015-09-11 | 2017-01-11 | 慧榮科技股份有限公司 | Data storage system and related method |
US10055282B1 (en) * | 2015-10-19 | 2018-08-21 | Marvell International Ltd. | Method and apparatus of feeding a seed value to a processing unit to initialize cyclic redundancy checking |
KR102473209B1 (en) * | 2015-12-14 | 2022-12-02 | 삼성전자주식회사 | Storage device and operating method of storage device |
KR102407437B1 (en) * | 2015-12-30 | 2022-06-10 | 삼성전자주식회사 | Memory system and electronic device including non-volatile memory module |
KR20170098538A (en) * | 2016-02-22 | 2017-08-30 | 에스케이하이닉스 주식회사 | Semiconductor device and driving method thereof |
KR20180033676A (en) * | 2016-09-26 | 2018-04-04 | 에스케이하이닉스 주식회사 | Memory module and memory system including the same |
US9934841B1 (en) * | 2016-10-21 | 2018-04-03 | Altera Corporation | Systems and methods for refreshing data in memory circuits |
KR20180089104A (en) * | 2017-01-31 | 2018-08-08 | 에스케이하이닉스 주식회사 | Memory module, memory system including the same and error correcting method thereof |
KR102483476B1 (en) * | 2018-04-03 | 2023-01-03 | 에스케이하이닉스 주식회사 | Semiconductor memory apparatus supporting repair with data I/O terminal as a unit and method of repairing the semiconductor memory apparatus |
KR102553780B1 (en) * | 2018-05-10 | 2023-07-10 | 에스케이하이닉스 주식회사 | Memory device, memory system including the same and operation method of the memory system |
KR20190132237A (en) * | 2018-05-18 | 2019-11-27 | 에스케이하이닉스 주식회사 | Memory system and operation method of memory system |
KR102538222B1 (en) * | 2018-06-26 | 2023-06-01 | 삼성전자주식회사 | Storage device, storage system including storage device, and method of accessing storage device |
US10725861B2 (en) * | 2018-06-28 | 2020-07-28 | Intel Corporation | Error correction code memory security |
KR102557993B1 (en) * | 2018-10-02 | 2023-07-20 | 삼성전자주식회사 | System on Chip and Memory system including security processor and Operating method of System on Chip |
-
2019
- 2019-01-24 KR KR1020190009054A patent/KR20200092036A/en active Search and Examination
- 2019-10-17 TW TW108137556A patent/TW202029209A/en unknown
- 2019-11-14 US US16/683,989 patent/US11216335B2/en active Active
- 2019-12-06 CN CN201911242329.8A patent/CN111475327B/en active Active
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11819504B2 (en) | 2018-08-26 | 2023-11-21 | Attain Health Inc. | Methods and compositions to increase hair growth and/or prevent hair loss |
WO2022125521A1 (en) * | 2020-12-09 | 2022-06-16 | Micron Technology, Inc. | Modified parity data using a poison data unit |
WO2022125372A1 (en) * | 2020-12-09 | 2022-06-16 | Micron Technology, Inc. | Modified checksum using a poison data pattern |
US11416331B2 (en) * | 2020-12-09 | 2022-08-16 | Micron Technology, Inc. | Modified checksum using a poison data pattern |
US20220391282A1 (en) * | 2020-12-09 | 2022-12-08 | Micron Technology, Inc. | Modified checksum using a poison data pattern |
US11714704B2 (en) * | 2020-12-09 | 2023-08-01 | Micron Technology, Inc. | Modified checksum using a poison data pattern |
US11775382B2 (en) | 2020-12-09 | 2023-10-03 | Micron Technology, Inc. | Modified parity data using a poison data unit |
US20220413763A1 (en) * | 2021-06-24 | 2022-12-29 | Phison Electronics Corp. | Mapping information management method, memory storage device and memory control circuit unit |
Also Published As
Publication number | Publication date |
---|---|
TW202029209A (en) | 2020-08-01 |
CN111475327A (en) | 2020-07-31 |
KR20200092036A (en) | 2020-08-03 |
CN111475327B (en) | 2023-10-03 |
US11216335B2 (en) | 2022-01-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11216335B2 (en) | Memory system and operation method thereof | |
US10152249B2 (en) | Data memory device and controller with interface error detection and handling logic | |
US11734106B2 (en) | Memory repair method and apparatus based on error code tracking | |
US9015558B2 (en) | Systems and methods for error detection and correction in a memory module which includes a memory buffer | |
US20170004037A1 (en) | Memory device with different parity regions | |
JP2011040051A5 (en) | ||
US20170160932A1 (en) | Reading Logical Groups of Data from Physical Locations in Memory Using Headers | |
CN104637534B (en) | Semiconductor memory device and method of operating the same | |
US10353770B2 (en) | Memory system and error correcting method of the same | |
US11256563B2 (en) | Memory controller with high data reliability, a memory system having the same, and an operation method of the memory controller | |
US11249844B2 (en) | Memory system and memory module | |
US11657890B2 (en) | Memory system, integrated circuit system, and operation method of memory system | |
US20120096335A1 (en) | Data processing method and semiconductor integrated circuit | |
US20190228833A1 (en) | Semiconductor systems | |
KR102023121B1 (en) | Memory device which corrects error and method of correcting error | |
US20210090684A1 (en) | Memory systems and methods of operating the memory systems | |
US10191807B2 (en) | Memory systems and operation method thereof | |
US10140025B2 (en) | Memory system including memory controller and operation method thereof | |
KR20180027656A (en) | Semiconductor device and semiconductor system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: SK HYNIX INC., KOREA, REPUBLIC OF Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:SHIN, WON-GYU;REEL/FRAME:051011/0557 Effective date: 20191022 |
|
FEPP | Fee payment procedure |
Free format text: ENTITY STATUS SET TO UNDISCOUNTED (ORIGINAL EVENT CODE: BIG.); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NOTICE OF ALLOWANCE MAILED -- APPLICATION RECEIVED IN OFFICE OF PUBLICATIONS |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: PUBLICATIONS -- ISSUE FEE PAYMENT VERIFIED |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |